xLAM-GGUF

xLAM - Blasphemer (GGUF)

This is an uncensored version of xLAM created using Blasphemer.

Model Details

• Base Model: Salesforce/Llama-xLAM-2-8b-fc-r
• Method: Abliteration (refusal direction removal)
• Format: GGUF (for llama.cpp, LM Studio, etc.)
• Quality Metrics:
  • Refusals: 2/100 (2%) ⭐ Excellent
  • KL Divergence: 0.00 ⭐ Excellent
  • Trial: #168 of 200

Quantization Versions

Usage

LM Studio

1. Download the GGUF file
2. Open LM Studio
3. Click "Import Model"
4. Select the downloaded file
5. Start chatting!

llama.cpp

./llama-cli -m xLAM-f16.gguf -p "Your prompt here"

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama(
    model_path="Llama-3.1-8B-Blasphemer-Q4_K_M.gguf",
    n_ctx=8192,
    n_gpu_layers=-1  # Use GPU
)

response = llm("Your prompt here", max_tokens=512)
print(response['choices'][0]['text'])

What is Abliteration?

Abliteration removes refusal behavior from language models by identifying and removing the neural directions responsible for safety alignment. This is done through:

1. Calculating refusal directions from harmful/harmless prompt pairs
2. Using Bayesian optimization (TPE) to find optimal removal parameters
3. Orthogonalizing model weights to these directions

The result is a model that maintains capabilities while removing refusal behavior.

Ethical Considerations

This model has reduced safety guardrails. Users are responsible for:

• Ensuring ethical use of the model
• Compliance with applicable laws and regulations
• Not using for illegal or harmful purposes
• Understanding the implications of reduced safety filtering

Performance

Compared to the original Llama:

• ✅ Follows instructions more directly
• ✅ Responds to previously refused queries
• ✅ Maintains general capabilities (KL divergence: 0.06)
• ⚠️ Reduced safety filtering

Credits

• Base Model: Salesforce (xLAM)
• Abliteration Tool: Blasphemer by Christopher Bradford
• Method: Based on "Refusal in Language Models Is Mediated by a Single Direction" (Arditi et al., 2024)

Citation

If you use this model, please cite:

@software{blasphemer2024,
  author = {Bradford, Christopher},
  title = {Blasphemer: Abliteration for Language Models},
  year = {2024},
  url = {https://github.com/sunkencity999/blasphemer}
}

@article{arditi2024refusal,
  title={Refusal in Language Models Is Mediated by a Single Direction},
  author={Arditi, Andy and Obmann, Oscar and Syed, Aaquib and others},
  journal={arXiv preprint arXiv:2406.11717},
  year={2024}
}

License

This model inherits the Llama 3.1 license from Meta AI. Please review the Llama 3.1 License for usage terms.